2

The following are data regarding a mammorgram:

  • In the absence of any special information, the probability that a woman (of the age and health status of this patient) has breast cancer is 1%.

  • If the patient has breast cancer, the probability that the radiologist will correctly diagnose it is 80%.

  • If the patient has a benign lesion (no breast cancer), the probability that the radiologist will incorrectly diagnose it as cancer is 10%.

What is the probability that a patient with a positive mammogram actually has breast cancer?

Let $B$ indicate breast cancer and $D$ indicate a correct diagnosis. Then $P(B) = .01, \ P(\neg B) = .99, \ P(D|B) = .8, \ P(\neg D | B) = .2, \ P(\neg D | \neg B) = .1, \ P(D | \neg B) = .9$

From Baye's Rule:

$\begin{equation} \begin{split} P(B|D) &= P(D|B)\times P(B) / \big [ P(D|B)\times P(B) + P(D|\neg B) \times P(\neg B)\big] \\ &= .8 \times .01 / [.8 \times .01 + .9 \times .99] \\ &= .039 \end{split} \end{equation}$

But my textbook (Rice, Mathematical Statistics and Data Analysis 3e, p. 23) says the answer is .075. What am I doing wrong?

Bram28
  • 100,612
  • 6
  • 70
  • 118
user_hello1
  • 765
  • 3
  • 11

1 Answers1

2

You define $D$ to be a correct diagnosis. That is not the same as a positive diagnosis.

So, let's use $P$ for Positive diagnosis.

Now you want to find $P(B|P)$.

You 'still' have:

$P(P|B)=.8$ and $P(\neg P|B)=.2$

But the crucial difference is:

$P(P|\neg B)=.1$ and $P(\neg P|\neg B)=.9$

OK, so try that.

Bram28
  • 100,612
  • 6
  • 70
  • 118